Security audit

Orc

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-style ORC reference skill; its examples can affect real data if copied into production, but the artifact itself does not hide execution, persistence, or data access.

Installers should treat this as a reference skill. Be careful copying its Spark overwrite, Hive UPDATE/DELETE/MERGE, and compaction examples into real systems because those operations can replace data or modify live tables; test on non-production data and verify target paths first.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: This shell skill is a code file, so SQP-2 applies to safety-relevant operations described within it. The Spark example uses mode("overwrite") to replace output data, but the surrounding help text provides no warning that this operation can overwrite existing files or datasets.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The file contains user-facing instructional content embedded in a shell script, and these SQL examples perform direct data changes and deletions. There is no adjacent caution, confirmation, or explanatory note warning users that the commands modify table contents and may be irreversible in practice.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 77% confidence
Finding: The major compaction command is an impactful maintenance operation that can significantly alter storage layout and affect running systems. The instructional text does not warn users about operational impact, resource usage, or the need to run such commands deliberately.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 86% confidence
Finding: These Spark write examples include mode="overwrite" and .mode("overwrite"), which can replace existing output paths. The file does not include any user-facing warning that these examples are destructive when pointed at existing locations.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.